WaveSpeed.ai
Home/Explore/Flux Image Tools/wavespeed-ai/flux-2-flex/text-to-image
text-to-image

text-to-image

FLUX.2 [flex]

wavespeed-ai/flux-2-flex/text-to-image

FLUX.2 [flex] from Black Forest Labs delivers fast, flexible text-to-image generation with enhanced realism, sharper text rendering, and built-in editing for rapid iteration: a ready-to-use REST inference API, best performance, no cold starts, and affordable pricing.

width
height
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

A vintage 1860s sepia-toned daguerreotype photograph. It depicts a serious Abraham Lincoln sitting in a formal chair, wearing his traditional suit and top hat, but he is wearing large, colorful, modern DJ headphones around his neck and holding a shiny silver microphone. The photo has scratches, dust particles, and heavy vignette typical of the 19th century, but the modern equipment looks physically present in the scene, not just pasted on.

Your request will cost $0.06 per run.

For $1 you can run this model approximately 16 times.

One more thing::

ExamplesView all

A vintage 1860s sepia-toned daguerreotype photograph. It depicts a serious Abraham Lincoln sitting in a formal chair, wearing his traditional suit and top hat, but he is wearing large, colorful, modern DJ headphones around his neck and holding a shiny silver microphone. The photo has scratches, dust particles, and heavy vignette typical of the 19th century, but the modern equipment looks physically present in the scene, not just pasted on.
A breathtaking photograph of "The Vertical Forest City." Enormous, futuristic residential skyscrapers built completely out of intertwining massive tree roots, glass, and polished wood, rising from a misty jungle canyon. Waterfalls cascade from the upper balconies of the buildings. Suspended glass bridges connect the towers. People are visible gardening on their plant-covered terraces. The architecture looks organic yet structurally impossible, bathed in warm sunset light.
A hyper-realistic close-up photograph of a master watchmaker's hands working on a complex mechanical watch movement. The watchmaker is using fine tweezers to carefully place a tiny ruby jewel bearing into the gears. We can see every wrinkle on the fingers, the tension in the skin, fingerprint ridges, and oil stains. The watch gears, springs, and tiny screws are rendered with immense mechanical precision under a magnifying lamp. The focus must be absolutely critical on the point where the tweezers touch the ruby.
A hyper-realistic studio shot of a transparent glass skull filled with colorful jelly beans. The skull is placed inside a cube made of clear ice. We can see the distorted refraction of the jelly beans through both the ice and the glass skull. Lighting is coming from behind, creating a glowing effect through the sweets. Water droplets are melting off the ice cube onto a black reflective surface.
A detailed, deconstructed technical blueprint of a futuristic sci-fi drone engine, drawn in white lines on a dark blue grid background. The schematic includes exploded views of gears and rotors. Specific components are labeled with text: "TURBINE V8", "INTAKE MANIFOLD", and "FUEL CELL". The drawing style is precise, engineering CAD style, with measurements and dashed lines indicating assembly.

README

FLUX.2 [flex] — Text-to-Image

FLUX.2 [flex] is the creative workhorse of the FLUX.2 family: a configurable, style-forward text-to-image model that delivers professional visuals while leaving plenty of room for experimentation. It is designed for teams who want more control over aesthetics and behaviour than a strictly “locked” production model.

Where FLUX.2 [flex] fits best

  • Style-driven exploration and concept art
  • High-volume generation where visual diversity is important
  • Brand and product imagery that needs frequent refinements
  • Fine-tuning experiments for domain- or brand-specific looks

Creative-first generation with control knobs

Rather than fixing all sampling behaviour, FLUX.2 [flex] keeps the lean FLUX.2 core but exposes more room to steer style, strength, and interpretation. You get production-usable images at good speed, while being able to push colour, mood, and composition further than with purely “set-and-forget” pipelines.

What you can get from this?

• Wide stylistic latitude

Produces a broad range of looks and moods—from clean product shots to heavily stylised illustration—so a single prompt can be explored in multiple creative directions.

• Tunable quality–speed trade-off

Supports configuration of inference settings, letting you run quick drafts cheaply and then dial up quality for shortlisted ideas or final renders.

• Open, extensible foundation

Built on open FLUX.2 tooling and community contributions, making it straightforward to inspect, adapt, and embed flex deeply into custom stacks.

• Friendly to LoRA and custom training

Works well as a base for LoRA adapters or other lightweight fine-tuning, so you can lock in house styles, specific subjects, or niche domains without retraining a heavyweight model.

• Resource-conscious for large runs

The streamlined architecture keeps GPU usage moderate, which is ideal for batch jobs, internal tools, and cost-sensitive creative pipelines.

• Consistent, repeatable results

Seed control and stable behaviour make it easy to recreate favourite generations or generate controlled variations for A/B tests and iterative design work.

Pricing

Simple per-image billing:

  • $0.06 per generated image

FLUX.2 family on WaveSpeedAI

Combine FLUX.2 [flex] with the rest of the FLUX.2 lineup for a complete creation and editing workflow:

More Image Tools on WaveSpeedAI

  • Nano Banana Pro – Google’s Gemini-based text-to-image model for sharp, coherent, prompt-faithful visuals that work great for ads, keyframes, and product shots.
  • Seedream V4 – ByteDance’s style-consistent, multi-image generator ideal for posters, campaigns, and large batches of on-brand illustrations.
  • Qwen Edit Plus – an enhanced Qwen-based image editor for precise inpainting, cleanup, and local style changes while preserving overall composition.